© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51778
    Prev
    Next
    INDEX
    Explanations

    parkway, speedway, byway, road

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ken
    -0.08
    ../
    -0.08
    NEL
    -0.08
    ald
    -0.08
    ним
    -0.08
    idue
    -0.08
     relay
    -0.07
    åħ¨çľģ
    -0.07
    ây
    -0.07
    rö
    -0.07
    POSITIVE LOGITS
    å¾ľ
    0.11
    æĭĪ
    0.11
    æ²īæµ¸åľ¨
    0.09
    髹
    0.09
    greens
    0.09
    çªĦ
    0.09
    theon
    0.09
    tics
    0.09
    NESS
    0.09
    oods
    0.09
    Activations Density 0.006%

    No Known Activations